Statistics – Machine Learning
Scientific paper
2011-07-22
Statistics
Machine Learning
Scientific paper
This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009) exhibit a policy such that with probability at least 1-1/n, the regret of the policy is of order log(n). They have also shown that such a property is not shared by the popular ucb1 policy of Auer et al. (2002). This work first answers an open question: it extends this negative result to any anytime policy. The second contribution of this paper is to design anytime robust policies for specific multi-armed bandit problems in which some restrictions are put on the set of possible distributions of the different arms.
Audibert Jean-Yves
Salomon Antoine
No associations
LandOfFree
Robustness of Anytime Bandit Policies does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Robustness of Anytime Bandit Policies, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Robustness of Anytime Bandit Policies will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-676511